network_profile 0.1.0
Sign up to get free protection for your applications and to get access to all the features.
- checksums.yaml +7 -0
- data/.github/workflows/verify.yml +23 -0
- data/.gitignore +10 -0
- data/.rspec +1 -0
- data/Gemfile +10 -0
- data/Gemfile.lock +92 -0
- data/LICENSE.txt +21 -0
- data/README.md +75 -0
- data/Rakefile +2 -0
- data/bin/console +14 -0
- data/bin/rake +29 -0
- data/bin/rspec +29 -0
- data/bin/setup +8 -0
- data/lib/network_profile.rb +23 -0
- data/lib/network_profile/extractor.rb +65 -0
- data/lib/network_profile/extractors/custom.rb +9 -0
- data/lib/network_profile/extractors/default_profile.rb +129 -0
- data/lib/network_profile/extractors/facebook_profile.rb +15 -0
- data/lib/network_profile/extractors/github_graphql.rb +24 -0
- data/lib/network_profile/extractors/github_profile.rb +98 -0
- data/lib/network_profile/extractors/github_project.rb +88 -0
- data/lib/network_profile/extractors/instagram_profile.rb +14 -0
- data/lib/network_profile/extractors/linkedin_profile.rb +14 -0
- data/lib/network_profile/extractors/network_profile_without_extraction.rb +25 -0
- data/lib/network_profile/extractors/researchgate_profile.rb +44 -0
- data/lib/network_profile/extractors/stackoverflow_profile.rb +81 -0
- data/lib/network_profile/extractors/upwork_profile.rb +42 -0
- data/lib/network_profile/extractors/xing_profile.rb +25 -0
- data/lib/network_profile/version.rb +3 -0
- data/network_profile.gemspec +31 -0
- metadata +132 -0
checksums.yaml
ADDED
@@ -0,0 +1,7 @@
|
|
1
|
+
---
|
2
|
+
SHA256:
|
3
|
+
metadata.gz: eaa6afbf057402529a5e99c22ff61b98b1af6bcb8ca03cd869ddf03ba0e6893f
|
4
|
+
data.tar.gz: 1cd9b2fe99baba7cbc8f6774d8cd981bffa7e6860349df584d7041e9bb23aeb9
|
5
|
+
SHA512:
|
6
|
+
metadata.gz: 93002910a6cb60f7ca0434b2231a583e440e2d4bc9a4e23e3721d021ee6af70acf959f0b012932f65dc175e5e209edba490add5780137d9e6afb9af3ebe6fa7b
|
7
|
+
data.tar.gz: 649cea60a5a341322cb3927aac5cd35b59bf374632694d9443c6dc37cfacf00a4afefe42336e350dce742d06c3ee81a3512eaf5407a82e31f10af77c5e86d97d
|
@@ -0,0 +1,23 @@
|
|
1
|
+
name: Verify
|
2
|
+
on: [push]
|
3
|
+
|
4
|
+
jobs:
|
5
|
+
tests:
|
6
|
+
name: Tests
|
7
|
+
runs-on: ubuntu-latest
|
8
|
+
strategy:
|
9
|
+
matrix:
|
10
|
+
# ruby: [ '2.5', '2.6', '2.7' ]
|
11
|
+
ruby: [ '2.6' ]
|
12
|
+
steps:
|
13
|
+
- uses: actions/checkout@v2
|
14
|
+
- uses: ruby/setup-ruby@v1
|
15
|
+
with:
|
16
|
+
ruby-version: ${{ matrix.ruby }}
|
17
|
+
- name: Install gems
|
18
|
+
run: |
|
19
|
+
bundle config path vendor/bundle
|
20
|
+
bundle install --jobs 4 --retry 3
|
21
|
+
- name: Run tests
|
22
|
+
run: bin/rspec
|
23
|
+
|
data/.gitignore
ADDED
data/.rspec
ADDED
@@ -0,0 +1 @@
|
|
1
|
+
--require spec_helper
|
data/Gemfile
ADDED
data/Gemfile.lock
ADDED
@@ -0,0 +1,92 @@
|
|
1
|
+
PATH
|
2
|
+
remote: .
|
3
|
+
specs:
|
4
|
+
network_profile (0.1.0)
|
5
|
+
activesupport (>= 5.0.0)
|
6
|
+
nokogiri
|
7
|
+
rdf-microdata
|
8
|
+
typhoeus
|
9
|
+
|
10
|
+
GEM
|
11
|
+
remote: https://rubygems.org/
|
12
|
+
specs:
|
13
|
+
activesupport (6.0.3.3)
|
14
|
+
concurrent-ruby (~> 1.0, >= 1.0.2)
|
15
|
+
i18n (>= 0.7, < 2)
|
16
|
+
minitest (~> 5.1)
|
17
|
+
tzinfo (~> 1.1)
|
18
|
+
zeitwerk (~> 2.2, >= 2.2.2)
|
19
|
+
addressable (2.7.0)
|
20
|
+
public_suffix (>= 2.0.2, < 5.0)
|
21
|
+
coderay (1.1.3)
|
22
|
+
concurrent-ruby (1.1.7)
|
23
|
+
crack (0.4.4)
|
24
|
+
diff-lcs (1.4.4)
|
25
|
+
ethon (0.12.0)
|
26
|
+
ffi (>= 1.3.0)
|
27
|
+
ffi (1.13.1)
|
28
|
+
hamster (3.0.0)
|
29
|
+
concurrent-ruby (~> 1.0)
|
30
|
+
hashdiff (1.0.1)
|
31
|
+
htmlentities (4.3.4)
|
32
|
+
i18n (1.8.5)
|
33
|
+
concurrent-ruby (~> 1.0)
|
34
|
+
link_header (0.0.8)
|
35
|
+
method_source (1.0.0)
|
36
|
+
mini_portile2 (2.4.0)
|
37
|
+
minitest (5.14.2)
|
38
|
+
nokogiri (1.10.10)
|
39
|
+
mini_portile2 (~> 2.4.0)
|
40
|
+
pry (0.13.1)
|
41
|
+
coderay (~> 1.1)
|
42
|
+
method_source (~> 1.0)
|
43
|
+
public_suffix (4.0.6)
|
44
|
+
rake (12.3.3)
|
45
|
+
rdf (3.1.6)
|
46
|
+
hamster (~> 3.0)
|
47
|
+
link_header (~> 0.0, >= 0.0.8)
|
48
|
+
rdf-microdata (3.1.1)
|
49
|
+
htmlentities (~> 4.3)
|
50
|
+
nokogiri (~> 1.10)
|
51
|
+
rdf (~> 3.1)
|
52
|
+
rdf-xsd (~> 3.1)
|
53
|
+
rdf-xsd (3.1.0)
|
54
|
+
rdf (~> 3.1)
|
55
|
+
rspec (3.9.0)
|
56
|
+
rspec-core (~> 3.9.0)
|
57
|
+
rspec-expectations (~> 3.9.0)
|
58
|
+
rspec-mocks (~> 3.9.0)
|
59
|
+
rspec-core (3.9.2)
|
60
|
+
rspec-support (~> 3.9.3)
|
61
|
+
rspec-expectations (3.9.2)
|
62
|
+
diff-lcs (>= 1.2.0, < 2.0)
|
63
|
+
rspec-support (~> 3.9.0)
|
64
|
+
rspec-mocks (3.9.1)
|
65
|
+
diff-lcs (>= 1.2.0, < 2.0)
|
66
|
+
rspec-support (~> 3.9.0)
|
67
|
+
rspec-support (3.9.3)
|
68
|
+
thread_safe (0.3.6)
|
69
|
+
typhoeus (1.4.0)
|
70
|
+
ethon (>= 0.9.0)
|
71
|
+
tzinfo (1.2.7)
|
72
|
+
thread_safe (~> 0.1)
|
73
|
+
vcr (6.0.0)
|
74
|
+
webmock (3.9.1)
|
75
|
+
addressable (>= 2.3.6)
|
76
|
+
crack (>= 0.3.2)
|
77
|
+
hashdiff (>= 0.4.0, < 2.0.0)
|
78
|
+
zeitwerk (2.4.0)
|
79
|
+
|
80
|
+
PLATFORMS
|
81
|
+
ruby
|
82
|
+
|
83
|
+
DEPENDENCIES
|
84
|
+
network_profile!
|
85
|
+
pry
|
86
|
+
rake (~> 12.0)
|
87
|
+
rspec (>= 3.5)
|
88
|
+
vcr
|
89
|
+
webmock
|
90
|
+
|
91
|
+
BUNDLED WITH
|
92
|
+
2.1.4
|
data/LICENSE.txt
ADDED
@@ -0,0 +1,21 @@
|
|
1
|
+
The MIT License (MIT)
|
2
|
+
|
3
|
+
Copyright (c) 2020 Stefan Wienert
|
4
|
+
|
5
|
+
Permission is hereby granted, free of charge, to any person obtaining a copy
|
6
|
+
of this software and associated documentation files (the "Software"), to deal
|
7
|
+
in the Software without restriction, including without limitation the rights
|
8
|
+
to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
|
9
|
+
copies of the Software, and to permit persons to whom the Software is
|
10
|
+
furnished to do so, subject to the following conditions:
|
11
|
+
|
12
|
+
The above copyright notice and this permission notice shall be included in
|
13
|
+
all copies or substantial portions of the Software.
|
14
|
+
|
15
|
+
THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
|
16
|
+
IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
|
17
|
+
FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
|
18
|
+
AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
|
19
|
+
LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
|
20
|
+
OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN
|
21
|
+
THE SOFTWARE.
|
data/README.md
ADDED
@@ -0,0 +1,75 @@
|
|
1
|
+
# NetworkProfile
|
2
|
+
|
3
|
+
Extractor Gem to analyse random strings for profile links of user. E.g. User uploads a PDF, scan it for all references to a social network profile.
|
4
|
+
|
5
|
+
This work is extracted from the German Applicant Tracking System EBMS (https://bms.empfehlungsbund.de).
|
6
|
+
|
7
|
+
## Installation
|
8
|
+
|
9
|
+
Add this line to your application's Gemfile:
|
10
|
+
|
11
|
+
```ruby
|
12
|
+
gem 'network_profile'
|
13
|
+
```
|
14
|
+
|
15
|
+
And then execute:
|
16
|
+
|
17
|
+
$ bundle install
|
18
|
+
|
19
|
+
Or install it yourself as:
|
20
|
+
|
21
|
+
$ gem install network_profile
|
22
|
+
|
23
|
+
## Usage
|
24
|
+
|
25
|
+
### Parse and extract one link
|
26
|
+
|
27
|
+
|
28
|
+
extraction = NetworkProfile.parse('https://github.com/zealot128', include_fallback_custom: true)
|
29
|
+
|
30
|
+
- ``include_fallback_custom: true`` uses the default extractor (og/meta-tags) if no other more specific extractor is found
|
31
|
+
- ``include_fallback_custom: false`` only use the specific website extractors and return nil if none matches the link
|
32
|
+
|
33
|
+
### Scan a whole long string for links
|
34
|
+
|
35
|
+
links = NetworkProfile::Extractor.call("Very long String with even broken links in it www . github . com/zealot128")
|
36
|
+
|
37
|
+
### Config
|
38
|
+
|
39
|
+
NetworkProfile.headers = {
|
40
|
+
'Accept' => 'text/html,application/xhtml+xml,application/xml;q=0.9,image/webp,*/*;q=0.8',
|
41
|
+
'Accept-Language' => 'de,en-US;q=0.7,en;q=0.3',
|
42
|
+
'Referer' => 'https://www.google.com',
|
43
|
+
'DNT' => '1',
|
44
|
+
'User-Agent' => 'Mozilla/5.0 (Macintosh; Intel Mac OS X 10.14; rv:73.0) Gecko/20100101 Firefox/73.0',
|
45
|
+
}
|
46
|
+
NetworkProfile.github_api_key = nil
|
47
|
+
|
48
|
+
|
49
|
+
## Extractor
|
50
|
+
|
51
|
+
The following network profiles are supported:
|
52
|
+
|
53
|
+
**GithubProfile/Company, GithubProject**:
|
54
|
+
|
55
|
+
- uses GH's GraphQL API (Thus a API KEY is required)
|
56
|
+
|
57
|
+
**Instagram** **Facebook** **Linkedin**
|
58
|
+
|
59
|
+
- Because those websites are closed and defensive as hell, there is no extraction, just a simple matching (e.g. "Facebook profile")
|
60
|
+
|
61
|
+
**Stackoverflow**
|
62
|
+
|
63
|
+
- Uses SO's API
|
64
|
+
|
65
|
+
**Upwork** **XING** **ResearchGate**
|
66
|
+
|
67
|
+
- Custom Website Scraper/Extract JSON+LD
|
68
|
+
|
69
|
+
**Default Fallback** (Custom)
|
70
|
+
|
71
|
+
- OG-Meta-Tags / HTML-Meta-Tags
|
72
|
+
|
73
|
+
## License
|
74
|
+
|
75
|
+
The gem is available as open source under the terms of the [MIT License](https://opensource.org/licenses/MIT).
|
data/Rakefile
ADDED
data/bin/console
ADDED
@@ -0,0 +1,14 @@
|
|
1
|
+
#!/usr/bin/env ruby
|
2
|
+
|
3
|
+
require "bundler/setup"
|
4
|
+
require "network_profile"
|
5
|
+
|
6
|
+
# You can add fixtures and/or initialization code here to make experimenting
|
7
|
+
# with your gem easier. You can also use a different console, if you like.
|
8
|
+
|
9
|
+
# (If you use this, don't forget to add pry to your Gemfile!)
|
10
|
+
# require "pry"
|
11
|
+
# Pry.start
|
12
|
+
|
13
|
+
require "irb"
|
14
|
+
IRB.start(__FILE__)
|
data/bin/rake
ADDED
@@ -0,0 +1,29 @@
|
|
1
|
+
#!/usr/bin/env ruby
|
2
|
+
# frozen_string_literal: true
|
3
|
+
|
4
|
+
#
|
5
|
+
# This file was generated by Bundler.
|
6
|
+
#
|
7
|
+
# The application 'rake' is installed as part of a gem, and
|
8
|
+
# this file is here to facilitate running it.
|
9
|
+
#
|
10
|
+
|
11
|
+
require "pathname"
|
12
|
+
ENV["BUNDLE_GEMFILE"] ||= File.expand_path("../../Gemfile",
|
13
|
+
Pathname.new(__FILE__).realpath)
|
14
|
+
|
15
|
+
bundle_binstub = File.expand_path("../bundle", __FILE__)
|
16
|
+
|
17
|
+
if File.file?(bundle_binstub)
|
18
|
+
if File.read(bundle_binstub, 300) =~ /This file was generated by Bundler/
|
19
|
+
load(bundle_binstub)
|
20
|
+
else
|
21
|
+
abort("Your `bin/bundle` was not generated by Bundler, so this binstub cannot run.
|
22
|
+
Replace `bin/bundle` by running `bundle binstubs bundler --force`, then run this command again.")
|
23
|
+
end
|
24
|
+
end
|
25
|
+
|
26
|
+
require "rubygems"
|
27
|
+
require "bundler/setup"
|
28
|
+
|
29
|
+
load Gem.bin_path("rake", "rake")
|
data/bin/rspec
ADDED
@@ -0,0 +1,29 @@
|
|
1
|
+
#!/usr/bin/env ruby
|
2
|
+
# frozen_string_literal: true
|
3
|
+
|
4
|
+
#
|
5
|
+
# This file was generated by Bundler.
|
6
|
+
#
|
7
|
+
# The application 'rspec' is installed as part of a gem, and
|
8
|
+
# this file is here to facilitate running it.
|
9
|
+
#
|
10
|
+
|
11
|
+
require "pathname"
|
12
|
+
ENV["BUNDLE_GEMFILE"] ||= File.expand_path("../../Gemfile",
|
13
|
+
Pathname.new(__FILE__).realpath)
|
14
|
+
|
15
|
+
bundle_binstub = File.expand_path("../bundle", __FILE__)
|
16
|
+
|
17
|
+
if File.file?(bundle_binstub)
|
18
|
+
if File.read(bundle_binstub, 300) =~ /This file was generated by Bundler/
|
19
|
+
load(bundle_binstub)
|
20
|
+
else
|
21
|
+
abort("Your `bin/bundle` was not generated by Bundler, so this binstub cannot run.
|
22
|
+
Replace `bin/bundle` by running `bundle binstubs bundler --force`, then run this command again.")
|
23
|
+
end
|
24
|
+
end
|
25
|
+
|
26
|
+
require "rubygems"
|
27
|
+
require "bundler/setup"
|
28
|
+
|
29
|
+
load Gem.bin_path("rspec-core", "rspec")
|
data/bin/setup
ADDED
@@ -0,0 +1,23 @@
|
|
1
|
+
require "network_profile/version"
|
2
|
+
require 'network_profile/extractor'
|
3
|
+
require 'network_profile/extractors/default_profile'
|
4
|
+
require 'active_support/core_ext/module/attribute_accessors'
|
5
|
+
|
6
|
+
module NetworkProfile
|
7
|
+
class Error < StandardError; end
|
8
|
+
|
9
|
+
mattr_accessor :headers, :github_api_key
|
10
|
+
|
11
|
+
self.headers = {
|
12
|
+
'Accept' => 'text/html,application/xhtml+xml,application/xml;q=0.9,image/webp,*/*;q=0.8',
|
13
|
+
'Accept-Language' => 'de,en-US;q=0.7,en;q=0.3',
|
14
|
+
'Referer' => 'https://www.google.com',
|
15
|
+
'DNT' => '1',
|
16
|
+
'User-Agent' => 'Mozilla/5.0 (Macintosh; Intel Mac OS X 10.14; rv:73.0) Gecko/20100101 Firefox/73.0',
|
17
|
+
}
|
18
|
+
self.github_api_key = nil
|
19
|
+
|
20
|
+
def self.parse(link, include_fallback_custom: false)
|
21
|
+
NetworkProfile::DefaultProfile.parse(link, include_fallback_custom: include_fallback_custom)
|
22
|
+
end
|
23
|
+
end
|
@@ -0,0 +1,65 @@
|
|
1
|
+
require 'active_support/core_ext/string/filters'
|
2
|
+
class NetworkProfile::Extractor
|
3
|
+
# Logic from:
|
4
|
+
# https://github.com/tenderlove/rails_autolink/blob/master/lib/rails_autolink/helpers.rb
|
5
|
+
AUTO_LINK_RE = %r{
|
6
|
+
(?: ((?:ed2k|ftp|http|https|irc|mailto|news|gopher|nntp|telnet|webcal|xmpp|callto|feed|svn|urn|aim|rsync|tag|ssh|sftp|rtsp|afs|file):)// | www\. )
|
7
|
+
[^\s<\u00A0"]+
|
8
|
+
}ix.freeze
|
9
|
+
WORD_PATTERN = '\p{Word}'.freeze
|
10
|
+
BRACKETS = { ']' => '[', ')' => '(', '}' => '{' }.freeze
|
11
|
+
|
12
|
+
def self.call(string)
|
13
|
+
new(string).extracted_links!
|
14
|
+
end
|
15
|
+
|
16
|
+
def initialize(string)
|
17
|
+
@string = string
|
18
|
+
end
|
19
|
+
|
20
|
+
def extracted_links!
|
21
|
+
extracted = links.map do |l|
|
22
|
+
NetworkProfile.parse(l)
|
23
|
+
rescue StandardError => e
|
24
|
+
p e
|
25
|
+
nil
|
26
|
+
end
|
27
|
+
extracted.compact
|
28
|
+
end
|
29
|
+
|
30
|
+
def links
|
31
|
+
return @links if @links
|
32
|
+
|
33
|
+
@links ||= []
|
34
|
+
mapped_string.scan(AUTO_LINK_RE) { |_|
|
35
|
+
scheme = Regexp.last_match(1)
|
36
|
+
href = $&
|
37
|
+
punctuation = []
|
38
|
+
while href.sub!(%r{[^#{WORD_PATTERN}/-=&]$}, '')
|
39
|
+
punctuation.push($&)
|
40
|
+
if opening = BRACKETS[punctuation.last] and href.scan(opening).size > href.scan(punctuation.last).size
|
41
|
+
href << punctuation.pop
|
42
|
+
break
|
43
|
+
end
|
44
|
+
end
|
45
|
+
href = 'https://' + href unless scheme
|
46
|
+
@links << href
|
47
|
+
}
|
48
|
+
@links.uniq
|
49
|
+
end
|
50
|
+
|
51
|
+
TLD = /(?<tld>com|de|net|fr|at|ch|info)/.freeze
|
52
|
+
HOST_PART = %r{(?<host>[a-z\-\.0-9]+)}.freeze
|
53
|
+
|
54
|
+
def mapped_string
|
55
|
+
@string.
|
56
|
+
gsub(%r{ (#{HOST_PART}\.#{TLD}/)}) { |_|
|
57
|
+
host = Regexp.last_match['host']
|
58
|
+
"https://#{host}.#{Regexp.last_match['tld']}/"
|
59
|
+
}.
|
60
|
+
gsub(%r{ www *\. +#{HOST_PART} *\. *#{TLD}(?<path>[^<\u00A0"]+)}) { |_|
|
61
|
+
path = Regexp.last_match['path'].remove(' ')
|
62
|
+
"www.#{Regexp.last_match['host']}.#{Regexp.last_match['tld']}#{path}"
|
63
|
+
}
|
64
|
+
end
|
65
|
+
end
|
@@ -0,0 +1,129 @@
|
|
1
|
+
require 'rdf/microdata'
|
2
|
+
require 'active_support/descendants_tracker'
|
3
|
+
require 'active_support/core_ext/module/attribute_accessors'
|
4
|
+
require 'active_support/core_ext/string/inflections'
|
5
|
+
require 'nokogiri'
|
6
|
+
require 'typhoeus'
|
7
|
+
|
8
|
+
module NetworkProfile
|
9
|
+
class DefaultProfile
|
10
|
+
include ActiveSupport::DescendantsTracker
|
11
|
+
|
12
|
+
cattr_accessor :mdi_icon
|
13
|
+
|
14
|
+
class << self
|
15
|
+
attr_accessor :headers
|
16
|
+
end
|
17
|
+
|
18
|
+
def self.auto_extractor_link_types
|
19
|
+
[
|
20
|
+
NetworkProfile::GithubProfile,
|
21
|
+
NetworkProfile::GithubProject,
|
22
|
+
NetworkProfile::LinkedinProfile,
|
23
|
+
NetworkProfile::InstagramProfile,
|
24
|
+
NetworkProfile::XingProfile,
|
25
|
+
NetworkProfile::ResearchgateProfile,
|
26
|
+
NetworkProfile::UpworkProfile,
|
27
|
+
NetworkProfile::FacebookProfile,
|
28
|
+
NetworkProfile::StackoverflowProfile,
|
29
|
+
].freeze
|
30
|
+
end
|
31
|
+
|
32
|
+
def self.all_types
|
33
|
+
auto_extractor_link_types + [NetworkProfile::Custom]
|
34
|
+
end
|
35
|
+
|
36
|
+
def self.parse(link, include_fallback_custom: false)
|
37
|
+
link_type = (include_fallback_custom ? all_types : auto_extractor_link_types).find { |i| i.handle?(link) }
|
38
|
+
if link_type
|
39
|
+
link_type.new(link.strip).data
|
40
|
+
end
|
41
|
+
end
|
42
|
+
|
43
|
+
def initialize(link)
|
44
|
+
@link = link
|
45
|
+
end
|
46
|
+
|
47
|
+
def image
|
48
|
+
img = doc.at('meta[property=og\:image]')&.[]('content')
|
49
|
+
if img && img[%r{^/\w+}]
|
50
|
+
img = URI.join(@link, img).to_s
|
51
|
+
end
|
52
|
+
img
|
53
|
+
end
|
54
|
+
|
55
|
+
def title
|
56
|
+
doc.at('title')&.text
|
57
|
+
end
|
58
|
+
|
59
|
+
def text
|
60
|
+
doc.at('meta[property=og\:description]')&.[]('content') || doc.at('meta[name=description]')&.[]('content')
|
61
|
+
end
|
62
|
+
|
63
|
+
def data
|
64
|
+
{
|
65
|
+
site_icon: mdi_icon,
|
66
|
+
link: @link,
|
67
|
+
title: title,
|
68
|
+
text: text,
|
69
|
+
image: image,
|
70
|
+
type: self.class.name.underscore.split('/').last
|
71
|
+
}.merge(extra_data)
|
72
|
+
end
|
73
|
+
|
74
|
+
def extra_data
|
75
|
+
{}
|
76
|
+
end
|
77
|
+
|
78
|
+
private
|
79
|
+
|
80
|
+
def response
|
81
|
+
@response ||= Typhoeus.get(@link, headers: NetworkProfile.headers, followlocation: true)
|
82
|
+
end
|
83
|
+
|
84
|
+
def doc
|
85
|
+
@doc ||= Nokogiri.parse(response.body)
|
86
|
+
end
|
87
|
+
|
88
|
+
def json_ld
|
89
|
+
@json_ld ||= JSON.parse(doc.search('script[type*=ld]').first.text)
|
90
|
+
end
|
91
|
+
|
92
|
+
def rdf
|
93
|
+
@rdf ||= map_rdf(
|
94
|
+
RDF::Microdata::Reader.new(response.body).to_h
|
95
|
+
)
|
96
|
+
end
|
97
|
+
|
98
|
+
def map_rdf(tree)
|
99
|
+
tree.
|
100
|
+
transform_keys { |v| map_rdf_value(v) }.
|
101
|
+
transform_values { |v| map_rdf_value(v) }
|
102
|
+
end
|
103
|
+
|
104
|
+
def map_rdf_value(value)
|
105
|
+
case value
|
106
|
+
when RDF::Vocabulary::Term then value.fragment
|
107
|
+
when RDF::URI then value.to_base
|
108
|
+
when RDF::Node then value.id
|
109
|
+
when RDF::Literal then value.value
|
110
|
+
when Hash then map_rdf(value)
|
111
|
+
when Array then value.map { |i| map_rdf_value(i) }
|
112
|
+
else
|
113
|
+
value
|
114
|
+
end
|
115
|
+
end
|
116
|
+
end
|
117
|
+
end
|
118
|
+
|
119
|
+
require_relative './custom'
|
120
|
+
require_relative './github_profile'
|
121
|
+
require_relative './github_project'
|
122
|
+
require_relative './linkedin_profile'
|
123
|
+
require_relative './instagram_profile'
|
124
|
+
require_relative './xing_profile'
|
125
|
+
require_relative './researchgate_profile'
|
126
|
+
require_relative './upwork_profile'
|
127
|
+
require_relative './facebook_profile'
|
128
|
+
require_relative './stackoverflow_profile'
|
129
|
+
|
@@ -0,0 +1,15 @@
|
|
1
|
+
require_relative './network_profile_without_extraction'
|
2
|
+
|
3
|
+
module NetworkProfile
|
4
|
+
class FacebookProfile < NetworkProfileWithoutExtraction
|
5
|
+
self.mdi_icon = 'facebook'
|
6
|
+
|
7
|
+
def self.handle?(link)
|
8
|
+
(e = link[%r{facebook.com/([\w\.]+)}, 1]) && e.length > 3 && e != 'groups'
|
9
|
+
end
|
10
|
+
|
11
|
+
def profile_description
|
12
|
+
"Facebook Profil:"
|
13
|
+
end
|
14
|
+
end
|
15
|
+
end
|
@@ -0,0 +1,24 @@
|
|
1
|
+
require 'active_support/core_ext/hash/indifferent_access'
|
2
|
+
|
3
|
+
module NetworkProfile::GithubGraphql
|
4
|
+
def query!(query)
|
5
|
+
r = Typhoeus.post("https://api.github.com/graphql",
|
6
|
+
body: { query: query }.to_json,
|
7
|
+
headers: {
|
8
|
+
"Authorization": "bearer #{NetworkProfile.github_api_key}"
|
9
|
+
})
|
10
|
+
if r.success?
|
11
|
+
JSON.parse(r.body).with_indifferent_access
|
12
|
+
else
|
13
|
+
raise ArgumentError, "Fetching query failed: #{r.code}"
|
14
|
+
end
|
15
|
+
end
|
16
|
+
|
17
|
+
def json
|
18
|
+
@json ||= query!(query)
|
19
|
+
end
|
20
|
+
|
21
|
+
def doc
|
22
|
+
raise NotImplementedError
|
23
|
+
end
|
24
|
+
end
|
@@ -0,0 +1,98 @@
|
|
1
|
+
require_relative './github_graphql'
|
2
|
+
|
3
|
+
module NetworkProfile
|
4
|
+
class GithubProfile < DefaultProfile
|
5
|
+
include GithubGraphql
|
6
|
+
self.mdi_icon = 'github'
|
7
|
+
|
8
|
+
def self.handle?(link)
|
9
|
+
link.to_s[%r{github.com/[^/]+/?$}] && NetworkProfile.github_api_key
|
10
|
+
end
|
11
|
+
|
12
|
+
def query
|
13
|
+
username = @link[%r{github.com/([^/]+)}, 1]
|
14
|
+
<<~DOC
|
15
|
+
query {
|
16
|
+
organization(login:"#{username}") {
|
17
|
+
avatarUrl
|
18
|
+
name
|
19
|
+
bio: description
|
20
|
+
location
|
21
|
+
websiteUrl
|
22
|
+
...RepoFragment
|
23
|
+
}
|
24
|
+
|
25
|
+
user(login:"#{username}") {
|
26
|
+
avatarUrl
|
27
|
+
name
|
28
|
+
bio
|
29
|
+
company
|
30
|
+
location
|
31
|
+
websiteUrl
|
32
|
+
followers {
|
33
|
+
totalCount
|
34
|
+
}
|
35
|
+
...RepoFragment
|
36
|
+
}
|
37
|
+
}
|
38
|
+
fragment RepoFragment on ProfileOwner {
|
39
|
+
pinnedItems(first: 9, types: [REPOSITORY]) {
|
40
|
+
edges {
|
41
|
+
node {
|
42
|
+
... on Repository {
|
43
|
+
nameWithOwner,
|
44
|
+
url,
|
45
|
+
createdAt,
|
46
|
+
updatedAt
|
47
|
+
stargazers { totalCount }
|
48
|
+
watchers {
|
49
|
+
totalCount
|
50
|
+
},
|
51
|
+
primaryLanguage {
|
52
|
+
name
|
53
|
+
}
|
54
|
+
}
|
55
|
+
}
|
56
|
+
}
|
57
|
+
}
|
58
|
+
}
|
59
|
+
DOC
|
60
|
+
end
|
61
|
+
|
62
|
+
def profile_data
|
63
|
+
json.dig('data', 'organization') || json.dig('data', 'user')
|
64
|
+
end
|
65
|
+
|
66
|
+
def title
|
67
|
+
profile_data['name']
|
68
|
+
end
|
69
|
+
|
70
|
+
def text
|
71
|
+
profile_data['bio']
|
72
|
+
end
|
73
|
+
|
74
|
+
def image
|
75
|
+
profile_data['avatarUrl']
|
76
|
+
end
|
77
|
+
|
78
|
+
def extra_data
|
79
|
+
{
|
80
|
+
company: profile_data['company'],
|
81
|
+
location: profile_data['location'],
|
82
|
+
profile_type: json.dig('data', 'organization') ? "organization" : "user",
|
83
|
+
followers: profile_data.dig('followers', 'totalCount'),
|
84
|
+
website: profile_data.dig('websiteUrl'),
|
85
|
+
pinned: profile_data.dig('pinnedItems', 'edges').map { |i|
|
86
|
+
n = i['node']
|
87
|
+
{ name: n['nameWithOwner'],
|
88
|
+
url: n['url'],
|
89
|
+
created: Time.parse(n['createdAt']).to_date,
|
90
|
+
updated: Time.parse(n['updatedAt']).to_date,
|
91
|
+
language: n.dig('primaryLanguage', 'name'),
|
92
|
+
stars: n['stargazers']['totalCount'],
|
93
|
+
watchers: n['watchers']['totalCount'] }
|
94
|
+
}
|
95
|
+
}
|
96
|
+
end
|
97
|
+
end
|
98
|
+
end
|
@@ -0,0 +1,88 @@
|
|
1
|
+
require_relative './github_graphql'
|
2
|
+
|
3
|
+
module NetworkProfile
|
4
|
+
class GithubProject < DefaultProfile
|
5
|
+
include GithubGraphql
|
6
|
+
self.mdi_icon = 'github'
|
7
|
+
|
8
|
+
def self.handle?(link)
|
9
|
+
link.to_s[%r{github.com/[^/]+/.+}] && NetworkProfile.github_api_key
|
10
|
+
end
|
11
|
+
|
12
|
+
def query
|
13
|
+
_, author, repo = @link.match(%r{github.com/([^/]+)/([^/\?]+)(\.git)?}).to_a
|
14
|
+
<<~DOC
|
15
|
+
query {
|
16
|
+
repository(name:"#{repo}", owner: "#{author}") {
|
17
|
+
createdAt
|
18
|
+
description
|
19
|
+
nameWithOwner
|
20
|
+
updatedAt
|
21
|
+
languages(first:10) {
|
22
|
+
edges {
|
23
|
+
node {
|
24
|
+
name
|
25
|
+
}
|
26
|
+
size
|
27
|
+
}
|
28
|
+
totalCount
|
29
|
+
}
|
30
|
+
licenseInfo { name }
|
31
|
+
forkCount
|
32
|
+
isFork
|
33
|
+
defaultBranchRef {
|
34
|
+
name
|
35
|
+
target {
|
36
|
+
... on Commit {
|
37
|
+
committedDate
|
38
|
+
history(first: 0) {
|
39
|
+
totalCount
|
40
|
+
}
|
41
|
+
}
|
42
|
+
}
|
43
|
+
}
|
44
|
+
issues {
|
45
|
+
totalCount
|
46
|
+
}
|
47
|
+
stargazers {
|
48
|
+
totalCount
|
49
|
+
}
|
50
|
+
watchers {
|
51
|
+
totalCount
|
52
|
+
}
|
53
|
+
}
|
54
|
+
}
|
55
|
+
DOC
|
56
|
+
end
|
57
|
+
|
58
|
+
def title
|
59
|
+
json.dig('data', 'repository', 'nameWithOwner')
|
60
|
+
end
|
61
|
+
|
62
|
+
def text
|
63
|
+
json.dig('data', 'repository', 'description')
|
64
|
+
end
|
65
|
+
|
66
|
+
def last_commit
|
67
|
+
Time.parse(json.dig('data', 'repository', 'defaultBranchRef', 'target', 'committedDate')).to_date
|
68
|
+
end
|
69
|
+
|
70
|
+
def image
|
71
|
+
nil
|
72
|
+
end
|
73
|
+
|
74
|
+
def extra_data
|
75
|
+
{
|
76
|
+
watchers: json.dig('data', 'repository', 'watchers', 'totalCount'),
|
77
|
+
forks: json.dig('data', 'repository', 'forkCount'),
|
78
|
+
stars: json.dig('data', 'repository', 'stargazers', 'totalCount'),
|
79
|
+
issue_count: json.dig('data', 'repository', 'issues', 'totalCount'),
|
80
|
+
commits: json.dig('data', 'repository', 'defaultBranchRef', 'target', 'history', 'totalCount'),
|
81
|
+
license: json.dig('data', 'repository', 'licenseInfo', 'name'),
|
82
|
+
created: Time.parse(json.dig('data', 'repository', 'createdAt')).to_date,
|
83
|
+
language_bytes: json.dig('data', 'repository', 'languages', 'edges')&.map { |l| [l.dig('node', 'name'), l['size']] }&.sort_by { |_a, b| -b },
|
84
|
+
last_commit: last_commit
|
85
|
+
}
|
86
|
+
end
|
87
|
+
end
|
88
|
+
end
|
@@ -0,0 +1,14 @@
|
|
1
|
+
require_relative './network_profile_without_extraction'
|
2
|
+
|
3
|
+
module NetworkProfile
|
4
|
+
class InstagramProfile < NetworkProfileWithoutExtraction
|
5
|
+
self.mdi_icon = 'instagram'
|
6
|
+
def self.handle?(link)
|
7
|
+
(e = link[%r{instagram.com/([\w\.]+)}, 1]) && e.length > 3 && e != 'groups'
|
8
|
+
end
|
9
|
+
|
10
|
+
def profile_description
|
11
|
+
"Instagram Profil:"
|
12
|
+
end
|
13
|
+
end
|
14
|
+
end
|
@@ -0,0 +1,14 @@
|
|
1
|
+
require_relative './network_profile_without_extraction'
|
2
|
+
|
3
|
+
module NetworkProfile
|
4
|
+
class LinkedinProfile < NetworkProfileWithoutExtraction
|
5
|
+
self.mdi_icon = 'linkedin'
|
6
|
+
def self.handle?(link)
|
7
|
+
link['linkedin.com/in/']
|
8
|
+
end
|
9
|
+
|
10
|
+
def profile_description
|
11
|
+
"LinkedIn Profil:"
|
12
|
+
end
|
13
|
+
end
|
14
|
+
end
|
@@ -0,0 +1,25 @@
|
|
1
|
+
require 'active_support/core_ext/string/inflections'
|
2
|
+
require_relative './default_profile.rb'
|
3
|
+
|
4
|
+
module NetworkProfile
|
5
|
+
class NetworkProfileWithoutExtraction < DefaultProfile
|
6
|
+
def profile_description
|
7
|
+
"Profil: "
|
8
|
+
end
|
9
|
+
|
10
|
+
def title
|
11
|
+
"#{profile_description} #{@link.split('/').last}"
|
12
|
+
end
|
13
|
+
|
14
|
+
def data
|
15
|
+
{
|
16
|
+
title: title,
|
17
|
+
text: "",
|
18
|
+
image: nil,
|
19
|
+
type: self.class.name.underscore.split('/').last,
|
20
|
+
link: @link,
|
21
|
+
site_icon: mdi_icon,
|
22
|
+
}
|
23
|
+
end
|
24
|
+
end
|
25
|
+
end
|
@@ -0,0 +1,44 @@
|
|
1
|
+
module NetworkProfile
|
2
|
+
class ResearchgateProfile < DefaultProfile
|
3
|
+
self.mdi_icon = ''
|
4
|
+
|
5
|
+
def self.handle?(link)
|
6
|
+
link['researchgate.net/profile/']
|
7
|
+
end
|
8
|
+
|
9
|
+
def json_ld
|
10
|
+
original = super
|
11
|
+
if original['@graph']
|
12
|
+
original['@graph'].first
|
13
|
+
else
|
14
|
+
original
|
15
|
+
end
|
16
|
+
end
|
17
|
+
|
18
|
+
def title
|
19
|
+
json_ld['name']
|
20
|
+
end
|
21
|
+
|
22
|
+
def text
|
23
|
+
json_ld.dig('affiliation', 'name') || doc.at('.org')&.text
|
24
|
+
end
|
25
|
+
|
26
|
+
def last_item
|
27
|
+
item = rdf.find { |_, v| v['type'].to_s['ScholarlyArticle'] }.last
|
28
|
+
return unless item
|
29
|
+
|
30
|
+
title = item.dig('<http://schema.org/headline>', 0)
|
31
|
+
date = item.dig('<http://schema.org/datePublished>', 0)
|
32
|
+
"#{title} (#{date})"
|
33
|
+
end
|
34
|
+
|
35
|
+
def extra_data
|
36
|
+
items, reads, citations = doc.at(".profile-content-item .nova-c-card").
|
37
|
+
search(".nova-o-grid__column").
|
38
|
+
map { |col| col.search('.nova-e-text').map(&:text) }.
|
39
|
+
map(&:first).map { |i| i.gsub(',', '').to_i }
|
40
|
+
|
41
|
+
{ items: items, reads: reads, citations: citations, last_item: last_item }
|
42
|
+
end
|
43
|
+
end
|
44
|
+
end
|
@@ -0,0 +1,81 @@
|
|
1
|
+
module NetworkProfile
|
2
|
+
# Tags:
|
3
|
+
# https://api.stackexchange.com/2.2/users/220292/top-tags?pagesize=10&site=stackoverflow
|
4
|
+
|
5
|
+
class StackoverflowProfile < DefaultProfile
|
6
|
+
self.mdi_icon = 'stack-overflow'
|
7
|
+
SITES = [
|
8
|
+
["https://stackoverflow.com", "stackoverflow", "Stack Overflow"],
|
9
|
+
["https://serverfault.com", "serverfault", "Server Fault"],
|
10
|
+
["https://superuser.com", "superuser", "Super User"],
|
11
|
+
["https://webapps.stackexchange.com", "webapps", "Web Applications"],
|
12
|
+
["https://gaming.stackexchange.com", "gaming", "Arqade"],
|
13
|
+
["https://webmasters.stackexchange.com", "webmasters", "Webmasters"],
|
14
|
+
["https://cooking.stackexchange.com", "cooking", "Seasoned Advice"],
|
15
|
+
["https://gamedev.stackexchange.com", "gamedev", "Game Development"],
|
16
|
+
["https://photo.stackexchange.com", "photo", "Photography"],
|
17
|
+
["https://stats.stackexchange.com", "stats", "Cross Validated"],
|
18
|
+
["https://math.stackexchange.com", "math", "Mathematics"],
|
19
|
+
["https://diy.stackexchange.com", "diy", "Home Improvement"],
|
20
|
+
["https://gis.stackexchange.com", "gis", "Geographic Information Systems"],
|
21
|
+
["https://tex.stackexchange.com", "tex", "TeX - LaTeX"],
|
22
|
+
["https://askubuntu.com", "askubuntu", "Ask Ubuntu"],
|
23
|
+
].freeze
|
24
|
+
|
25
|
+
def self.handle?(link)
|
26
|
+
SITES.any? { |s, _, _| link.include?(s + "/users/") }
|
27
|
+
end
|
28
|
+
|
29
|
+
def site
|
30
|
+
@site ||= SITES.find { |s, _, _| @link.include?(s) }
|
31
|
+
end
|
32
|
+
|
33
|
+
def title
|
34
|
+
user_api['display_name']
|
35
|
+
end
|
36
|
+
|
37
|
+
def image
|
38
|
+
user_api['profile_image']
|
39
|
+
end
|
40
|
+
|
41
|
+
def text
|
42
|
+
end
|
43
|
+
|
44
|
+
def extra_data
|
45
|
+
{
|
46
|
+
reputation: user_api.dig('reputation'),
|
47
|
+
created: Time.at(user_api['creation_date']).to_date,
|
48
|
+
location: user_api.dig('location'),
|
49
|
+
site: site[2],
|
50
|
+
site_logo: "https://cdn.sstatic.net/Sites/#{site[1]}/img/apple-touch-icon.png",
|
51
|
+
tags: tags_api.map { |j| [j['tag_name'], j['answer_score'] + j['question_score']] }
|
52
|
+
}
|
53
|
+
end
|
54
|
+
|
55
|
+
def user_id
|
56
|
+
URI.parse(@link).path[%r{/users/(\d+)/?}, 1]
|
57
|
+
end
|
58
|
+
|
59
|
+
private
|
60
|
+
|
61
|
+
def user_api
|
62
|
+
@user_api ||=
|
63
|
+
begin
|
64
|
+
url = "https://api.stackexchange.com/2.2/users/#{user_id}?order=desc&sort=reputation&site=#{site[1]}"
|
65
|
+
api_call(url).dig('items', 0)
|
66
|
+
end
|
67
|
+
end
|
68
|
+
|
69
|
+
def tags_api
|
70
|
+
@tags_api ||=
|
71
|
+
begin
|
72
|
+
url = "https://api.stackexchange.com/2.2/users/#{user_id}/top-tags?pagesize=10&site=#{site[1]}"
|
73
|
+
api_call(url).dig('items')
|
74
|
+
end
|
75
|
+
end
|
76
|
+
|
77
|
+
def api_call(url)
|
78
|
+
JSON.parse(Typhoeus.get(url, accept_encoding: 'gzip').body)
|
79
|
+
end
|
80
|
+
end
|
81
|
+
end
|
@@ -0,0 +1,42 @@
|
|
1
|
+
require 'active_support/core_ext/string/filters'
|
2
|
+
|
3
|
+
module NetworkProfile
|
4
|
+
class UpworkProfile < DefaultProfile
|
5
|
+
self.mdi_icon = 'upwork'
|
6
|
+
def self.handle?(link)
|
7
|
+
link[%r{upwork.com/o/profiles/users/.+}]
|
8
|
+
end
|
9
|
+
|
10
|
+
def title
|
11
|
+
php_vars.dig('profile', 'profile', 'name')
|
12
|
+
end
|
13
|
+
|
14
|
+
def text
|
15
|
+
doc.at('h2 strong').text
|
16
|
+
end
|
17
|
+
|
18
|
+
def php_vars
|
19
|
+
@php_vars ||=
|
20
|
+
begin
|
21
|
+
t = doc.search('script').find { |i| i && i.text['PROFILE_RESPONSE'] }.text
|
22
|
+
t.remove!(/window.PROFILE_RESPONSE=.*summary:/)
|
23
|
+
JSON.parse(t.remove(/\}$/))
|
24
|
+
end
|
25
|
+
end
|
26
|
+
|
27
|
+
def extra_data
|
28
|
+
profile = php_vars.dig('profile')
|
29
|
+
rate = profile.dig('stats', 'hourlyRate')
|
30
|
+
{
|
31
|
+
country: profile.dig('profile', 'location').yield_self { |v| "#{v['city']}, #{v['country']}" },
|
32
|
+
hours: profile.dig('stats', 'totalHours').floor,
|
33
|
+
jobs: profile.dig('stats', 'totalJobsWorked').floor,
|
34
|
+
rating: profile.dig('stats', 'rating').round(2),
|
35
|
+
hourly_rate: "#{rate['amount']} #{rate['currencyCode']}",
|
36
|
+
english_level: profile['stats']['englishLevel'],
|
37
|
+
hire_again: profile.dig('stats', 'hireAgainPercentage'),
|
38
|
+
skills: profile.dig('profile', 'skills').map { |i| i['prettyName'] }
|
39
|
+
}
|
40
|
+
end
|
41
|
+
end
|
42
|
+
end
|
@@ -0,0 +1,25 @@
|
|
1
|
+
module NetworkProfile
|
2
|
+
class XingProfile < DefaultProfile
|
3
|
+
self.mdi_icon = 'xing'
|
4
|
+
|
5
|
+
def self.handle?(link)
|
6
|
+
link['xing.com/profile/']
|
7
|
+
end
|
8
|
+
|
9
|
+
def title
|
10
|
+
doc.at('h1').text.strip
|
11
|
+
end
|
12
|
+
|
13
|
+
def text
|
14
|
+
json_ld.dig('jobTitle')
|
15
|
+
end
|
16
|
+
|
17
|
+
def extra_data
|
18
|
+
{
|
19
|
+
employment_status: doc.at('[data-qa=xing-id-work_experience]')&.text&.split(', ')&.first,
|
20
|
+
tags: json_ld&.fetch('makesOffer', [])&.map { |i| i['name'] } || [],
|
21
|
+
languages: doc.at('[data-qa=language-skills-section]')&.search('li')&.map { |i| "#{i.at('h3').text} (#{i.at('div').text})" },
|
22
|
+
}
|
23
|
+
end
|
24
|
+
end
|
25
|
+
end
|
@@ -0,0 +1,31 @@
|
|
1
|
+
require_relative 'lib/network_profile/version'
|
2
|
+
|
3
|
+
Gem::Specification.new do |spec|
|
4
|
+
spec.name = "network_profile"
|
5
|
+
spec.version = NetworkProfile::VERSION
|
6
|
+
spec.authors = ["Stefan Wienert"]
|
7
|
+
spec.email = ["info@stefanwienert.de"]
|
8
|
+
|
9
|
+
spec.summary = %q{Extract profile metadata from various social-media-profiles}
|
10
|
+
spec.description = %q{Extract profile metadata from various social-media-profiles, such as Twitter, XING, Github, Stackoverflow or generic og-metatags.}
|
11
|
+
spec.homepage = "https://github.com/pludoni/network_profile"
|
12
|
+
spec.license = "MIT"
|
13
|
+
spec.required_ruby_version = Gem::Requirement.new(">= 2.3.0")
|
14
|
+
|
15
|
+
spec.metadata["homepage_uri"] = spec.homepage
|
16
|
+
spec.metadata["source_code_uri"] = "https://github.com/pludoni/network_profile"
|
17
|
+
# spec.metadata["changelog_uri"] = "TODO: Put your gem's CHANGELOG.md URL here."
|
18
|
+
|
19
|
+
# Specify which files should be added to the gem when it is released.
|
20
|
+
# The `git ls-files -z` loads the files in the RubyGem that have been added into git.
|
21
|
+
spec.files = Dir.chdir(File.expand_path('..', __FILE__)) do
|
22
|
+
`git ls-files -z`.split("\x0").reject { |f| f.match(%r{^(test|spec|features)/}) }
|
23
|
+
end
|
24
|
+
spec.bindir = "exe"
|
25
|
+
spec.executables = spec.files.grep(%r{^exe/}) { |f| File.basename(f) }
|
26
|
+
spec.require_paths = ["lib"]
|
27
|
+
spec.add_dependency "typhoeus"
|
28
|
+
spec.add_dependency "rdf-microdata"
|
29
|
+
spec.add_dependency "activesupport", ">= 5.0.0"
|
30
|
+
spec.add_dependency "nokogiri"
|
31
|
+
end
|
metadata
ADDED
@@ -0,0 +1,132 @@
|
|
1
|
+
--- !ruby/object:Gem::Specification
|
2
|
+
name: network_profile
|
3
|
+
version: !ruby/object:Gem::Version
|
4
|
+
version: 0.1.0
|
5
|
+
platform: ruby
|
6
|
+
authors:
|
7
|
+
- Stefan Wienert
|
8
|
+
autorequire:
|
9
|
+
bindir: exe
|
10
|
+
cert_chain: []
|
11
|
+
date: 2020-09-22 00:00:00.000000000 Z
|
12
|
+
dependencies:
|
13
|
+
- !ruby/object:Gem::Dependency
|
14
|
+
name: typhoeus
|
15
|
+
requirement: !ruby/object:Gem::Requirement
|
16
|
+
requirements:
|
17
|
+
- - ">="
|
18
|
+
- !ruby/object:Gem::Version
|
19
|
+
version: '0'
|
20
|
+
type: :runtime
|
21
|
+
prerelease: false
|
22
|
+
version_requirements: !ruby/object:Gem::Requirement
|
23
|
+
requirements:
|
24
|
+
- - ">="
|
25
|
+
- !ruby/object:Gem::Version
|
26
|
+
version: '0'
|
27
|
+
- !ruby/object:Gem::Dependency
|
28
|
+
name: rdf-microdata
|
29
|
+
requirement: !ruby/object:Gem::Requirement
|
30
|
+
requirements:
|
31
|
+
- - ">="
|
32
|
+
- !ruby/object:Gem::Version
|
33
|
+
version: '0'
|
34
|
+
type: :runtime
|
35
|
+
prerelease: false
|
36
|
+
version_requirements: !ruby/object:Gem::Requirement
|
37
|
+
requirements:
|
38
|
+
- - ">="
|
39
|
+
- !ruby/object:Gem::Version
|
40
|
+
version: '0'
|
41
|
+
- !ruby/object:Gem::Dependency
|
42
|
+
name: activesupport
|
43
|
+
requirement: !ruby/object:Gem::Requirement
|
44
|
+
requirements:
|
45
|
+
- - ">="
|
46
|
+
- !ruby/object:Gem::Version
|
47
|
+
version: 5.0.0
|
48
|
+
type: :runtime
|
49
|
+
prerelease: false
|
50
|
+
version_requirements: !ruby/object:Gem::Requirement
|
51
|
+
requirements:
|
52
|
+
- - ">="
|
53
|
+
- !ruby/object:Gem::Version
|
54
|
+
version: 5.0.0
|
55
|
+
- !ruby/object:Gem::Dependency
|
56
|
+
name: nokogiri
|
57
|
+
requirement: !ruby/object:Gem::Requirement
|
58
|
+
requirements:
|
59
|
+
- - ">="
|
60
|
+
- !ruby/object:Gem::Version
|
61
|
+
version: '0'
|
62
|
+
type: :runtime
|
63
|
+
prerelease: false
|
64
|
+
version_requirements: !ruby/object:Gem::Requirement
|
65
|
+
requirements:
|
66
|
+
- - ">="
|
67
|
+
- !ruby/object:Gem::Version
|
68
|
+
version: '0'
|
69
|
+
description: Extract profile metadata from various social-media-profiles, such as
|
70
|
+
Twitter, XING, Github, Stackoverflow or generic og-metatags.
|
71
|
+
email:
|
72
|
+
- info@stefanwienert.de
|
73
|
+
executables: []
|
74
|
+
extensions: []
|
75
|
+
extra_rdoc_files: []
|
76
|
+
files:
|
77
|
+
- ".github/workflows/verify.yml"
|
78
|
+
- ".gitignore"
|
79
|
+
- ".rspec"
|
80
|
+
- Gemfile
|
81
|
+
- Gemfile.lock
|
82
|
+
- LICENSE.txt
|
83
|
+
- README.md
|
84
|
+
- Rakefile
|
85
|
+
- bin/console
|
86
|
+
- bin/rake
|
87
|
+
- bin/rspec
|
88
|
+
- bin/setup
|
89
|
+
- lib/network_profile.rb
|
90
|
+
- lib/network_profile/extractor.rb
|
91
|
+
- lib/network_profile/extractors/custom.rb
|
92
|
+
- lib/network_profile/extractors/default_profile.rb
|
93
|
+
- lib/network_profile/extractors/facebook_profile.rb
|
94
|
+
- lib/network_profile/extractors/github_graphql.rb
|
95
|
+
- lib/network_profile/extractors/github_profile.rb
|
96
|
+
- lib/network_profile/extractors/github_project.rb
|
97
|
+
- lib/network_profile/extractors/instagram_profile.rb
|
98
|
+
- lib/network_profile/extractors/linkedin_profile.rb
|
99
|
+
- lib/network_profile/extractors/network_profile_without_extraction.rb
|
100
|
+
- lib/network_profile/extractors/researchgate_profile.rb
|
101
|
+
- lib/network_profile/extractors/stackoverflow_profile.rb
|
102
|
+
- lib/network_profile/extractors/upwork_profile.rb
|
103
|
+
- lib/network_profile/extractors/xing_profile.rb
|
104
|
+
- lib/network_profile/version.rb
|
105
|
+
- network_profile.gemspec
|
106
|
+
homepage: https://github.com/pludoni/network_profile
|
107
|
+
licenses:
|
108
|
+
- MIT
|
109
|
+
metadata:
|
110
|
+
homepage_uri: https://github.com/pludoni/network_profile
|
111
|
+
source_code_uri: https://github.com/pludoni/network_profile
|
112
|
+
post_install_message:
|
113
|
+
rdoc_options: []
|
114
|
+
require_paths:
|
115
|
+
- lib
|
116
|
+
required_ruby_version: !ruby/object:Gem::Requirement
|
117
|
+
requirements:
|
118
|
+
- - ">="
|
119
|
+
- !ruby/object:Gem::Version
|
120
|
+
version: 2.3.0
|
121
|
+
required_rubygems_version: !ruby/object:Gem::Requirement
|
122
|
+
requirements:
|
123
|
+
- - ">="
|
124
|
+
- !ruby/object:Gem::Version
|
125
|
+
version: '0'
|
126
|
+
requirements: []
|
127
|
+
rubyforge_project:
|
128
|
+
rubygems_version: 2.7.6
|
129
|
+
signing_key:
|
130
|
+
specification_version: 4
|
131
|
+
summary: Extract profile metadata from various social-media-profiles
|
132
|
+
test_files: []
|